Measuring Goal-directedness

Abstract

We define maximum entropy goal-directedness (MEG), a formal measure of goal-directedness in causal models and Markov decision processes, and give algorithms for computing it. Measuring goal-directedness is important, as it is a critical element of many concerns about harm from AI. It is also of philosophical interest, as goal-directedness is a key aspect of agency. MEG is based on an adaptation of the maximum causal entropy framework used in inverse reinforcement learning. It can measure goal-directedness with respect to a known utility function, a hypothesis class of utility functions, or a set of random variables. We prove that MEG satisfies several desiderata and demonstrate our algorithms with small-scale experiments.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymacdermott2024measuring

Related papers

• Towards Measuring Goal-directedness In AI Systems (2024)0.00
• Provably Efficient Maximum Entropy Exploration (2018)0.00
• Task-agnostic Exploration Via Policy Gradient Of A Non-parametric State Entropy Estimate (2020)0.00
• Maximum Entropy-regularized Multi-goal Reinforcement Learning (2019)0.00
• Maximum Causal Entropy IRL In Mean-field Games And GNEP Framework For Forward RL (2024)0.00
• Maximum Entropy Gain Exploration For Long Horizon Multi-goal Reinforcement Learning (2020)0.00
• Goal Discovery With Causal Capacity For Efficient Reinforcement Learning (2025)0.00
• The Importance Of Non-markovianity In Maximum State Entropy Exploration (2022)0.00